Microsoft staff have demonstrated an early prototype of a realistic avatar created using Kinect’s facial mesh and mapping abilities. See it in action through the break.
Craig Mundie, Microsoft’s chief research and strategy officer, said the new system could achieve near photo quality, and could even be extended to the whole body.
“There’s no reason that we couldn’t do that in real time by feeding the information that we get from a Kinect sensor, including its audio input and its 3D modelling spatial representation, and couple that to the body and the gesture recognition in order to create a full body avatar that has photorealistic features and full facial recognition,” he said.
“This is obviously still research work, so it’ll be some time before it shows up in products,” he added.
You can catch the demo yourself below, courtesy of USA Today.